Skip to main content
Glama
camoran89

Satrack Documentation Generator MCP

by camoran89
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
executeA

Herramienta unificada del MCP de documentación Satrack. IMPORTANTE: este MCP corre en un servidor remoto y NO accede al filesystem del usuario. El cliente (agente IDE) DEBE: (a) llamar get_documentation_rules para obtener AGENTS.md (fuente de verdad), (b) leer los archivos del workspace con sus propias herramientas y enviar su contenido en sourceFiles cuando aplique, (c) tomar la respuesta del MCP como punto de partida y ajustarla a AGENTS.md, (d) escribir los archivos finales en disco localmente. Todas las acciones se invocan pasando action + params (JSON string). Acciones:

  • get_user_info: Verifica sesión Azure AD. params: {} | { token: "..." } (token solo para validación puntual; para autenticación permanente coloca el sk-... en mcp.json -> headers.Authorization)

  • generate_documentation: Devuelve AGENTS.md + plantillas a escribir LOCALMENTE. params: { outputPath, projectName, siteName, sourceFiles?, ... }. sourceFiles debe contener el contenido (no rutas) leído por el agente.

  • get_documentation_rules: Lee AGENTS.md del servidor (LLAMAR PRIMERO). params: {}

  • get_autogen_guide: Lee autogen-guide.md. params: {}

  • get_component_generation_prompt: Obtiene prompt de componentes. params: {}

  • report_validation: Registra reporte en BD. params: { analysis_type, user, files_analyzed, findings, summary, ... }

  • publish_documentation: Publica en Azure Storage. params: { projectPath, siteName?, skipBuild? }

  • generate_architecture_documentation: Docs multi-proyecto. params: { outputPath, architectureName, siteName, rootPath? | projects? }

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4/5.0

Scored across 1 tool

Disambiguation1/5

There is only one tool named 'execute' that handles all actions, making it impossible for an agent to distinguish between distinct operations at the tool-selection level. The actions are embedded as parameters, but the tool itself is a vague catch-all.

Naming Consistency1/5

The single tool name 'execute' is a generic verb that does not follow the standard verb_noun pattern used by well-designed MCP servers. The internal actions have consistent naming (e.g., get_documentation_rules, generate_documentation), but they are not exposed as separate tools.

Tool Count1/5

With a tool count of 1, the server collapses at least 8 distinct operations into a single monolithic dispatcher. This is an extreme mismatch for the scope, which clearly warrants separate tools for rule retrieval, documentation generation, publishing, and reporting.

Completeness4/5

The embedded actions cover the core documentation workflow: retrieving rules, generating docs, validating, publishing, and handling architecture documentation. There are minor gaps (e.g., no update/delete for published docs), but the primary lifecycle is represented.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources